Portable digital intelligent human body thermal comfort portable detection device and method

Abstract

The invention provides a portable digital intelligent human body thermal comfort portable detection device and method. The detection device comprises an intelligent bracelet, an intelligent tool, an intelligent safety helmet, a wireless communication module and a management terminal. The intelligent bracelet is provided with a thermal comfort evaluation model, physiological parameters, psychological parameters and underground environment parameters of an operator are monitored through the intelligent bracelet, the intelligent tool and the intelligent safety helmet respectively, all the parameters are gathered to the intelligent bracelet, and the thermal comfort evaluation model is called through the intelligent bracelet. The current thermal comfort level is obtained based on the collected physiological parameters, psychological parameters and underground environment parameters; and triggering grading early warning according to the thermal comfort grade. By adopting the device and the method provided by the invention, the accuracy of predicting the thermal comfort of the human body in the underground environment is improved, meanwhile, the individuation of thermal comfort prediction is reflected, and thermal comfort trending pre-judgment is realized by utilizing historical information.

Description

Technical Field

[0001] This invention belongs to the field of health monitoring of underground miners, and specifically relates to a portable, digital, and intelligent personal thermal comfort detection device and method. Background Technology

[0002] In recent years, resource extraction has been rapidly expanding into high-altitude and deep-mining areas, leading to a continuous deterioration of the mining environment. The low pressure and low oxygen levels at high altitudes, combined with the high temperature and humidity in deep mines, create a dual environmental stress that not only severely impacts mining safety but also poses a significant threat to the occupational health of underground workers, severely affecting their physiological and psychological well-being. Thermal comfort is a comprehensive result of physiological and psychological factors, as well as objective and subjective factors. However, current safety regulations only consider dry-bulb temperature as the sole indicator for evaluating underground heat hazards. Therefore, researching a portable, digitally-enabled personal thermal comfort detection device and method, and constructing a real-time collaborative monitoring system for human thermal comfort, is of great significance for addressing safety and health issues in extreme mining environments.

[0003] Current research on human thermal comfort largely focuses on thermophysiological changes in indoor environments, while research in mining environments is not yet fully mature. For assessing human thermal comfort, the Predicted Mean Vote (PMV) method is commonly used. This method integrates environmental and individual factors through an expression to reflect the average thermal sensation of the group.

[0004] (1) However, the PMV model, proposed by Fanger based on steady-state thermal equilibrium theory, assumes that the human body is in thermal equilibrium, environmental parameters are stable, labor load is fixed, and clothing thermal resistance is well-defined. However, in the underground mining environment, environmental parameters such as temperature and humidity are unevenly distributed along the roadway, resulting in systematic deviations from the assumptions of the PMV model. At the same time, medium to high-intensity physical labor is common underground, and the metabolic rate of workers changes dynamically with fatigue caused by continuous work. The metabolic rate values ​​used in the PMV model are mostly static lookup table data, which are difficult to match the dynamic changes in labor intensity in real time. The above factors lead to a large error in the thermal comfort prediction of the PMV model in underground mining scenarios, significantly limiting its applicability.

[0005] (2) In addition, existing portable detection devices (such as smart bracelets, environmental sensors, etc.) usually only collect single types of parameters, with relatively simple functions. Furthermore, there is a lack of collaborative working mechanisms between different devices, making it difficult to uniformly model and comprehensively analyze multi-source heterogeneous data such as human physiological parameters, environmental parameters, and psychological parameters. Under these circumstances, existing technologies often rely on a single indicator to judge the human thermal comfort state, resulting in inaccurate evaluation results.

[0006] (3) Furthermore, there are significant individual differences among downhole workers. The threshold of traditional heat hazard early warning methods is based on the statistical laws of the population and is a fixed static value. It does not take into account the individual dynamic adjustment needs and cannot be dynamically adjusted according to the individual's physiological baseline, heat tolerance and the cumulative effect of continuous operation. Therefore, it is difficult to reflect individuality and cannot use historical information to make trend predictions.

[0007] (4) Secondly, the human body's tolerance to thermal environments varies significantly under different work scenarios. For example, in ground-level or well-ventilated indoor environments, even when workers are in a state of high labor intensity, their heat dissipation conditions are relatively good, and they have a wide range of adaptability to changes in ambient temperature and humidity, resulting in relatively low thermal comfort requirements. However, in enclosed, poorly ventilated, and complex thermal and humidity environments such as underground mines, workers are more likely to experience heat accumulation and increased physiological load under high-intensity labor conditions. Even if the change in ambient temperature is not significant, it may still have a significant adverse impact on human comfort and health. However, existing detection equipment and evaluation methods usually use a single environmental parameter or a single physiological indicator to judge personnel comfort and health risks. Most of them fail to comprehensively consider multiple factors such as environmental parameters, human physiological state, and work intensity at the same time, and lack the ability to dynamically characterize the differences in human thermal response under different work scenarios. It is difficult to accurately reflect changes in personnel comfort and potential health risks during actual work. Summary of the Invention

[0008] To address the problems in the prior art, the present invention aims to provide a portable, intelligent human thermal comfort detection device and method, so as to improve the accuracy of predicting human thermal comfort in the downhole environment, while also reflecting the personalization of thermal comfort prediction and realizing the use of historical information to predict thermal comfort trends.

[0009] To achieve the above objectives, the present invention adopts the following technical solution:

[0010] This invention provides a portable, intelligent, wearable device for detecting human thermal comfort, comprising a smart bracelet, smart tooling, a smart helmet, a wireless communication module, and a management terminal. The smart bracelet, smart tooling, and smart helmet are interconnected via Bluetooth, and the smart bracelet and management terminal are electrically connected via the wireless communication module. The smart bracelet is equipped with a thermal comfort assessment model. The smart bracelet, smart tooling, and smart helmet monitor the physiological parameters, psychological parameters, and underground environmental parameters of the worker, respectively. All parameters are aggregated in the smart bracelet, which then calls the thermal comfort assessment model to derive the current thermal comfort level based on the collected physiological, psychological, and underground environmental parameters. A graded warning is triggered based on the thermal comfort level.

[0011] Furthermore, the smart bracelet includes a smart bracelet body, a heart rate detection module, a blood oxygen detection module, a pulse detection module, a bracelet Bluetooth module, a wireless communication module, a display module, an interaction module, a bracelet local processing module, a positioning module, and a bracelet battery; the heart rate detection module, blood oxygen detection module, pulse detection module, display module, interaction module, positioning module, bracelet Bluetooth module, and wireless communication module are respectively electrically connected to the bracelet local processing module, and the bracelet battery supplies power to each of the smart bracelet's power-consuming modules.

[0012] Furthermore, the intelligent tooling includes an intelligent tooling body, main intelligent tooling equipment, tooling switch, ambient temperature detection module, ambient humidity detection module, tooling local processing module, tooling Bluetooth module, and tooling battery; the ambient temperature detection module and ambient humidity detection module are electrically connected to the tooling local processing module, and the tooling battery supplies power to each power-consuming module of the intelligent tooling and controls its on / off state through the tooling switch.

[0013] Furthermore, the smart safety helmet includes a smart safety helmet body, a safety helmet switch, an LED module, a vibration module, a forehead temperature detection module, a safety helmet Bluetooth module, a microcontroller module, and a safety helmet battery. The LED module, vibration module, and forehead temperature detection module are electrically connected to the microcontroller module. The safety helmet battery supplies power to each of the smart safety helmet's electrical modules and controls their on / off states through the safety helmet switch.

[0014] The management terminal is a data center located on the ground, including at least one computer server and its supporting data storage devices, communication interface devices and data processing software, used to receive, store, analyze and manage various types of data uploaded by the underground wearable detection devices.

[0015] Another aspect of the present invention provides a portable method for detecting human thermal comfort using the above-mentioned detection device, comprising the following steps:

[0016] S1: Establish a thermal comfort assessment model; deploy the thermal comfort assessment model to the wristband's local processing module;

[0017] S2: Connect smart bracelets, smart work clothes, and smart safety helmets via Bluetooth, and bind worker information to the smart bracelets;

[0018] S3: The smart bracelet, smart tooling and smart safety helmet are used to monitor the physiological parameters, psychological parameters and underground environmental parameters of the workers respectively. All parameters are summarized to the local processing module of the bracelet.

[0019] S4: The thermal comfort assessment model is called through the local processing module of the wristband, and the current thermal comfort level is obtained based on the parameters obtained in S3; and a graded warning is triggered according to the thermal comfort level.

[0020] Furthermore, the process of establishing the thermal comfort assessment model includes the following steps:

[0021] S11: Questionnaire Survey

[0022] Three representative high-altitude mines were selected as research subjects. Questionnaire surveys and basic information collection were conducted among the workers. Subjective thermal sensations, comfort evaluations, and personal basic information of the workers under different environmental conditions, labor intensity, and working hours were obtained. Combined with corresponding environmental parameters and working condition data, a thermal comfort assessment sample library for high-altitude mine working scenarios was constructed. This thermal comfort assessment sample library serves as the basic data support for the establishment of thermal comfort assessment models, parameter correction, and result verification.

[0023] Considering the long-term dynamic changes in the mining environment and external conditions, the thermal comfort assessment sample database is set to have a five-year validity period and will be periodically updated after the expiration of the validity period. During the update process, questionnaire surveys and data collection will be carried out again to correct the sample distribution and parameter range in the thermal comfort assessment sample database.

[0024] The necessity of such periodic updates stems from at least the following factors: phased changes in climatic conditions, differences in environmental characteristics in high-altitude areas, continuous changes in mining depth, evolution of technologies such as ventilation and cooling, and adjustments in operational processes and labor organization. All of these factors can affect workers' thermal adaptability, thermal perception characteristics, and comfort assessments. By setting a fixed update cycle, it is possible to ensure that the thermal comfort assessment database remains consistent with the actual working environment, thereby improving the applicability and reliability of the assessment method across different time scales and operational stages.

[0025] Before developing a thermal comfort assessment method, preliminary data preparation work was carried out targeting typical working groups and working environments to ensure the scientific validity, applicability, and long-term effectiveness of the assessment results.

[0026] S12: Sample Collection

[0027] Core physiological and environmental parameters for thermal assessment were collected using smart bracelets, smart workwear, and smart safety helmets. A web-based questionnaire sent via the smart bracelets collected data on participants' gender, age, clothing thermal resistance, activity intensity, and thermal comfort voting. Forehead temperature, heart rate, blood oxygen, pulse, ambient temperature, ambient humidity, clothing thermal resistance, and human activity status were collected as input samples. Human thermal comfort was quantified into Thermal Comfort Voting Values ​​(TSVs) using the ISO 7730 seven-level scale. The corresponding thermal comfort levels were collected as output samples via the web-based questionnaire. Over 1000 valid questionnaires were collected, forming the input-output sample pairs required for supervised learning.

[0028] S13: Data Preprocessing

[0029] The raw data was cleaned, outliers were removed using box plots, and missing values ​​were filled using Lagrange interpolation to ensure the quality of the training samples. Next, feature selection was performed, removing low-variance and highly correlated features and retaining nine effective features: ambient temperature, ambient humidity, heart rate, blood oxygen, pulse, forehead temperature, clothing thermal resistance, work intensity, and personnel identity. Normalization was then applied. Finally, the dataset was split: stratified sampling was performed in a 7:3 ratio to create a training set (for model learning) and a test set (for generalization validation). Numerical features were standardized to unify features of different dimensions into a trainable range. Thermal comfort levels were discretized into classification labels, and then divided into training and test sets in a 7:3 ratio for model training and evaluation.

[0030] S14: Model Training and Optimization

[0031] Multiple classification models were constructed using logistic regression, random forest, gradient boosting decision tree (GBDT), and support vector machine (SVM) algorithms. Model parameters were optimized through cross-validation and grid search. Evaluation metrics included accuracy and F1-score, and the best-performing model was selected. During training, the model continuously learned the mapping relationship between input features and thermal comfort levels, achieving comprehensive discrimination ability of multi-dimensional core parameters.

[0032] S15: Model Deployment and Real-Time Application

[0033] The trained optimal model is lightweighted and then deployed to the local processing module of the wristband to achieve real-time computing at the edge. During the application, multi-dimensional core thermal parameters collected in real time are used as input samples to the model, and the current thermal comfort level of the worker is output. The model output can be used for display on the display module, triggering graded early warnings, and uploading data to the remote management terminal to achieve real-time thermal comfort status assessment and personalized safety management.

[0034] The real-time data obtained by S3 is displayed through the display module; users can switch screen pages and view detailed data through touch operation.

[0035] Furthermore, the real-time data obtained from S3 is transmitted to the management terminal via the wireless communication module. The management terminal classifies and stores the data to form a personal thermal comfort history database for each worker. The management terminal integrates the stored historical information of the workers with the transmitted real-time data to comprehensively assess the suitability of the worker's current physical condition for continuous work and outputs a binary decision result: "It is recommended to continue working" or "It is recommended to take a break". The decision result is simultaneously pushed to the worker's smart bracelet and safety helmet.

[0036] Furthermore, the positioning module obtains the real-time location information of the workers. Based on the obtained real-time location information of the workers and the corresponding thermal comfort status data, the management terminal dynamically delineates dangerous areas and safe areas and executes control commands.

[0037] This invention constructs a thermal comfort assessment model based on sample data from mining operation scenarios and trains it using machine learning algorithms. The machine learning algorithms include, but are not limited to, logistic regression, random forest, gradient boosting decision tree (GBDT), and support vector machine (SVM).

[0038] The physiological parameters of this invention include heart rate, blood oxygen, pulse, and forehead temperature data, which are collected by the heart rate detection module, blood oxygen detection module, pulse detection module of the smart bracelet, and forehead temperature detection module in the smart safety helmet, respectively. The underground environmental parameters include air temperature and humidity data of the working area, which are collected by the environmental temperature detection module and environmental humidity detection module inside the smart tooling, respectively. The psychological parameters include thermal sensation voting information and thermal comfort satisfaction evaluation information, which are obtained through the interaction module of the smart bracelet.

[0039] Furthermore, before workers enter the mine, their smart wristbands automatically generate a recognizable QR code. At the mine entrance, facial recognition equipment verifies the worker's identity while scanning the QR code generated by the smart wristband, linking the worker's identity information with the unique identifiers of the smart wristband, smart workwear, and safety helmet. This linking information is simultaneously uploaded to the management terminal for storage. This achieves a one-to-one mapping between personnel and equipment, ensuring that all subsequently collected data is traceable to the specific worker.

[0040] Furthermore, in step S4, on the one hand, the real-time location information of the worker is obtained through the positioning module. Combined with the thermal comfort level output in step S4, if an abnormal state is determined, a graded early warning mechanism is triggered: when it is a mild abnormality, a prompt signal is sent to the smart bracelet worn by the worker, and the vibration module built into the safety helmet worn by the worker emits a low-frequency prompt, while the LED module of the smart safety helmet emits a low-frequency flash; when it is a severe abnormality, an alarm signal is simultaneously sent to the management terminal, real-time location information is uploaded, and the vibration module built into the safety helmet emits a high-frequency alarm, the LED module of the smart safety helmet emits a high-frequency flash, and emergency response measures are activated in conjunction with the alarm. On the one hand, based on changes in physiological parameters, the display module displays the human body's thermal comfort level in real time using four safety colors matched according to the level of danger, enabling intuitive identification of the risk status. The specific correspondence is as follows: severe abnormality level ("hot" or "cold" in thermal comfort level) is displayed in red, mild abnormality level ("warm" or "cool" in thermal comfort level) is displayed in yellow, normal level ("slightly warm" or "slightly cool" in thermal comfort level) is displayed in blue, and comfortable level ("moderate" in thermal comfort level) is displayed in green. The safety colors are displayed synchronously with the text information of thermal comfort level, and the color brightness is adapted to the complex lighting environment underground, ensuring that workers can quickly identify the current thermal comfort risk status.

[0041] Considering the high noise levels in mining operations and the need for workers to wear protective gear, the frequency design of the vibration module built into the safety helmet must meet two requirements: it must avoid the resonant frequencies of the equipment during operation, while ensuring that the vibration signal can penetrate the protective gear and be effectively sensed. The low-frequency vibration of 150-170Hz is relatively gentle and will not interfere with normal operation, making it suitable as a warning signal; the high-frequency vibration of 190-235Hz is strongly perceptible and can quickly transmit emergency warnings. This frequency range is technically easy to implement, and the vibration intensity is moderate, ensuring that it will neither damage the equipment nor affect operational safety.

[0042] Based on the historical patterns of individual thermophysiological characteristics, a correlation mapping between "history and current" data is constructed. By quantitatively analyzing the matching degree between the current state and the individual's safety threshold, personalized operational risk assessment can be achieved. This avoids excessive intervention for personnel with strong heat tolerance, while providing early warnings for sensitive groups, thus balancing mine operation efficiency and personnel safety.

[0043] Beneficial effects

[0044] 1. By working together with smart wristbands, smart workwear and smart safety helmets, and achieving data interconnection among the three based on Bluetooth, the system can simultaneously collect the physiological parameters (heart rate, blood oxygen, pulse, forehead temperature), psychological parameters (thermal comfort vote, satisfaction evaluation) and underground environmental parameters (air temperature, humidity) of the workers in real time, and summarize them to the local processing module of the wristband to achieve synchronous fusion of multimodal parameters.

[0045] 2. Based on samples of core thermal evaluation parameters and corresponding geothermal evaluation levels, a thermal comfort assessment model is constructed using machine learning. This model, combined with real-time collected data on the core thermal evaluation parameters of the workers, determines their current thermal comfort level. This model can comprehensively analyze multi-dimensional parameters, overcoming the limitations of traditional fixed-threshold evaluation methods. When a single indicator is abnormal, it is not necessary to directly determine the thermal comfort level; instead, a more realistic thermal comfort assessment result is derived by comprehensively considering all core parameters. This overcomes the drawbacks of evaluating thermal comfort levels using one or more fixed thresholds, effectively improving the accuracy of thermal comfort assessment.

[0046] 3. The thermal comfort assessment model is deployed in the wristband's local processing module, instantly calculating the thermal comfort level of workers based on real-time collected parameters. Combined with location information and management terminals, it can provide graded early warnings for mild or severe anomalies, and respond quickly through wristband display, vibration alerts, LED prompts, and integrated remote alarms, thereby improving the safety of underground operations.

[0047] 4. By using QR codes and facial recognition, a one-to-one binding between operators and equipment is achieved, ensuring that all collected data is traceable to specific individuals. The integration of historical and real-time data allows for the creation of individualized operational risk profiles, providing a scientific basis for safety management and health control.

[0048] 5. By integrating multi-dimensional core parameters with machine learning models, dynamic and personalized thermal comfort assessments are achieved, significantly improving the accuracy of assessments in extreme mining environments. Compared to traditional single-parameter or fixed-threshold methods, this invention comprehensively considers physiological, psychological, and environmental factors, making thermal comfort assessments more consistent with actual operating conditions, while simultaneously improving safety and operational efficiency.

[0049] 6. This invention constructs a multi-device collaborative data acquisition system, realizing the fusion and correlation of cross-modal information at the data layer, feature layer, and decision layer. It integrates human physiological parameters, downhole environmental parameters, and psychological parameters into multimodal data, fully exploring the inherent correlation and complementary relationship between different modal data, and effectively overcoming the cognitive limitations brought about by single device or single parameter evaluation methods. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 This is an overall flowchart of the human thermal comfort detection method of the present invention.

[0052] Figure 2 This is a schematic diagram of the external structure of a smart safety helmet.

[0053] Figure 3 This is a schematic diagram of the structure of each module of the smart safety helmet.

[0054] Figure 4 This is a schematic diagram of the external structure of a smart bracelet.

[0055] Figure 5 This is a schematic diagram of the structure of each module of the smart bracelet.

[0056] Figure 6 This is a schematic diagram of a smart bracelet display.

[0057] Figure 7 This is a schematic diagram of the external structure of the intelligent tooling.

[0058] Figure 8 This is a schematic diagram of the structure of each module of the intelligent tooling.

[0059] Figure 9 This is a diagram illustrating how to wear it.

[0060] Figure 10 This is a diagram illustrating the data interaction between the various devices.

[0061] In the diagram: 1. Smart helmet main body; 2. Helmet battery; 3. Vibration module; 4. LED module; 5. Helmet switch; 6. Forehead temperature detection module; 7. Helmet Bluetooth module; 8. Microcontroller module; 9. Smart bracelet main body; 10. Heart rate detection module; 11. Blood oxygen detection module; 12. Pulse detection module; 13. Interaction module; 14. Positioning module; 15. Wireless communication module; 16. Bracelet Bluetooth module; 17. Bracelet local processing module; 18. Bracelet battery; 19. Display module; 20. Smart tooling main body; 21. Main equipment of smart tooling; 22. Ambient temperature detection module; 23. Ambient humidity detection module; 24. Tooling local processing module; 25. Tooling Bluetooth module; 26. Tooling battery; 27. Tooling switch. Detailed Implementation

[0062] To make the technical problems, technical solutions, and beneficial effects to be solved by this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and are not intended to limit the scope of this application.

[0063] It should be noted that when a component is referred to as being "fixed to" or "set on" another component, it can be directly on or indirectly on that other component. When a component is referred to as being "connected to" another component, it can be directly connected to or indirectly connected to that other component.

[0064] It should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0065] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0066] Reference Figures 2 to 10 This embodiment provides a portable, intelligent, wearable device for detecting human thermal comfort, including a smart bracelet, smart tooling, a smart safety helmet, a wireless communication module, and a management terminal. The smart bracelet, smart tooling, and smart safety helmet are interconnected via Bluetooth, and the smart bracelet and management terminal are electrically connected via the wireless communication module. The smart bracelet is equipped with a thermal comfort assessment model. The smart bracelet, smart tooling, and smart safety helmet monitor the physiological parameters, psychological parameters, and underground environmental parameters of the worker, respectively. All parameters are aggregated in the smart bracelet, which then calls the thermal comfort assessment model to derive the current thermal comfort level based on the collected physiological, psychological, and underground environmental parameters. A graded warning is triggered based on the thermal comfort level.

[0067] The smart bracelet includes a main body 9, a heart rate detection module 10, a blood oxygen detection module 11, a pulse detection module 12, a Bluetooth module 16, a wireless communication module 15, a display module 19, an interaction module 13, a local processing module 17, a positioning module 14, and a battery 18. The heart rate detection module, blood oxygen detection module, pulse detection module, display module, interaction module, positioning module, Bluetooth module, and wireless communication module are electrically connected to the local processing module, and the battery powers each of the smart bracelet's power-consuming modules.

[0068] The intelligent tooling includes an intelligent tooling body 20, intelligent tooling main equipment 21, tooling switch 27, ambient temperature detection module 22, ambient humidity detection module 23, tooling local processing module 24, tooling Bluetooth module 25, and tooling battery 26. The ambient temperature detection module and ambient humidity detection module are electrically connected to the tooling local processing module, and the tooling battery supplies power to each power module of the intelligent tooling and controls the on / off state through the tooling switch.

[0069] The smart safety helmet includes a main body 1, a safety helmet switch 5, an LED module 4, a vibration module 3, a forehead temperature detection module 6, a safety helmet Bluetooth module 7, a microcontroller module 8, and a safety helmet battery 2. The LED module, vibration module, and forehead temperature detection module are electrically connected to the microcontroller module. The safety helmet battery supplies power to each of the smart safety helmet's electrical modules and controls their on / off states through the safety helmet switch.

[0070] The management terminal is a data center located on the ground, including at least one computer server and its supporting data storage devices, communication interface devices and data processing software, used to receive, store, analyze and manage various types of data uploaded by the underground wearable detection devices.

[0071] The following will elaborate further:

[0072] The LED module 4 is located in the front viewing window area of ​​the helmet body 1. The helmet switch 5 is used to control the start and stop of the module. The forehead temperature detection module 6 is located in the front viewing window area of ​​the visor of the helmet body 1 and is used to detect the forehead temperature of the worker. The helmet Bluetooth module 7 is used for wireless communication. The vibration module 3 is located in the rear area of ​​the helmet body 1 and is used to provide vibration reminders.

[0073] The forehead temperature detection module 6 is placed close to the worker's forehead to collect forehead temperature data in real time and transmit it to the microcontroller module 8; the safety helmet Bluetooth module 7 is wirelessly connected to the smart bracelet 9, which can upload forehead temperature data and status information, or receive remote control commands; the safety helmet switch 5 is used to turn the entire smart safety helmet on / off, and the LED module 4 can display different lights according to the needs of the scene (such as a constant light for normal operation and a flashing light for warning); if the system prompts an abnormality, the microcontroller module 8 triggers the vibration module 3 to generate a vibration reminder, and at the same time controls the LED module 4 to emit a warning light signal.

[0074] After the worker puts on the helmet, they turn on switch 5, and the system starts automatically. Forehead temperature detection module 6 continuously monitors body temperature, and safety helmet Bluetooth module 7 enables data interaction, facilitating centralized management of the worker's status from the backend. In case of abnormalities, the system provides dual alerts through vibration and light. The LED module 4's lights can serve as a warning in complex environments (such as nighttime work or warning of dangerous areas).

[0075] refer to Figures 3 to 5 The smart bracelet body 9 is equipped with a heart rate detection module 10, a blood oxygen detection module 11, a pulse detection module 12, an interaction module 13, a positioning module 14, a wireless communication module 15, a bracelet Bluetooth module 16, a local processing module 17, a bracelet battery 18, and a display module 19. The bracelet battery 18 supplies power to the various power modules of the smart bracelet. The local processing module 17 is electrically connected to the heart rate detection module 10, blood oxygen detection module 11, pulse detection module 12, interaction module 13, positioning module 14, wireless communication module 15, bracelet Bluetooth module 16, and display module 19. The heart rate detection module 10, blood oxygen detection module 11, and pulse detection module 12 are used to collect user physiological index data; the positioning module 14 is used to obtain the bracelet's location information; the wireless communication module 15 and the bracelet Bluetooth module 16 are used for multi-mode wireless communication; the interaction module 13 is used for human-computer interaction operation; and the display module 19 is used to display data and information, the displayed information being for reference. Figure 5 .

[0076] The wristband battery 18 uses a rechargeable lithium battery to power all the smart wristband's power modules; the local processing module 17, as the core control unit, is responsible for the entire process scheduling of data acquisition, analysis, and transmission. The physiological detection modules—heart rate detection module 10, blood oxygen detection module 11, and pulse detection module 12—are closely attached to the user's wrist skin, collecting real-time physiological data such as heart rate, blood oxygen saturation, and pulse, and transmitting the data to the wristband's local processing module 17; the positioning and communication module—positioning module 14—obtains the smart wristband's location information; the wireless communication module 15 enables remote data uploading and command reception; the wristband's Bluetooth module 16 is used for short-range interconnection with peripheral devices such as smart workwear and smart safety helmets; the interaction and display module—interaction module 13—supports user operations such as function switching and parameter settings; the display module 19 displays real-time physiological data, thermal comfort level, time, and other information.

[0077] After the user wears the smart bracelet, the physiological detection module continuously collects data, which is then analyzed and processed by the local processing module 17 and presented by the display module 19. The location information and physiological data can be uploaded to the management terminal through the wireless communication module 15. The interaction module 13 can trigger specific functions according to the user's needs (such as setting a heart rate warning threshold).

[0078] The main body 20 of the intelligent tooling is equipped with a main intelligent tooling device 21 located at the upper end of the arm. The main intelligent tooling device 21 integrates an environmental temperature detection module 22, an environmental humidity detection module 23, a local processing module 24, a tooling Bluetooth module 25, a tooling battery 26, and a tooling switch 27. The tooling battery 26 uses a rechargeable lithium battery to power all power-consuming modules. The tooling local processing module 24, as the core control unit, is responsible for the collection, processing, and transmission scheduling of environmental data. The environmental detection modules 22 and 23 are in direct contact with the working environment, collecting real-time temperature and humidity data and transmitting the raw data to the local processing module 24. The tooling Bluetooth module 25 establishes a wireless connection with the smart bracelet, uploading the processed environmental data to the management terminal for data visualization and remote monitoring. The tooling switch 27 is used for manual control of the device's on / off operation, allowing operators to flexibly operate the device according to scenario requirements.

[0079] After the operator puts on the smart tooling main body 20, they turn on the tooling switch 27, and the equipment starts up immediately. The ambient temperature detection module 22 and the ambient humidity detection module 23 continuously collect temperature and humidity data of the surrounding environment. After being analyzed and processed by the local processing module 24, the data is transmitted in real time to the associated external device (smart bracelet) via the tooling Bluetooth module 25. The operator can view the real-time temperature and humidity curves and historical data on the smart bracelet. When environmental parameters exceed the threshold, the external device can trigger an audible and visual alert to ensure that the operator is aware of the environmental anomaly and can take appropriate measures.

[0080] The wearing requirements for portable thermal comfort testing devices can be found in the following references. Figure 9 The smart safety helmet 1 is worn on the worker's head, and the helmet is adjusted to fit the head properly, ensuring that the forehead temperature detection module 6 is close enough to the worker's forehead. Simultaneously, components such as the LED module 4 and vibration module 3 are unobstructed and function normally, thus effectively enabling the collection of head physiological parameters and the warning function. The smart bracelet 9 is worn on the worker's wrist, and the tightness is adjusted so that the heart rate detection module 10, blood oxygen detection module 11, and pulse detection module 12 fit well against the wrist skin. The display module 19 and interaction module 13 are oriented in a direction convenient for the worker to observe and operate, ensuring the accuracy of hand physiological parameter collection and the convenience of human-computer interaction. The smart workwear 20 is worn on the worker's torso, and the main body 20 is adjusted to fit the worker's body shape, ensuring that the main equipment 21 of the smart workwear (integrated environmental temperature detection module 22, environmental humidity detection module 23, etc.) is in an unobstructed area on the outside of the torso, thus ensuring the real-time and comprehensive collection of temperature and humidity parameters of the working environment.

[0081] Through the above-mentioned wearable operation, the smart safety helmet 1, smart bracelet 9, and smart workwear 20 can be arranged in a coordinated manner, providing a reliable hardware configuration guarantee for the synchronous detection of multi-dimensional parameters of thermal comfort.

[0082] refer to Figure 10 This diagram illustrates the data interaction between the smart safety helmet, smart bracelet, smart workwear, and management terminal in this invention. The system uses the smart bracelet as a multi-source data aggregation and processing center, and achieves collaborative interaction of worker physiological parameters, environmental parameters, and thermal comfort assessment results through a combination of Bluetooth and wireless communication.

[0083] Specifically, the smart helmet and smart bracelet establish a connection via Bluetooth. A forehead temperature detection module within the smart helmet collects the worker's forehead temperature data and transmits this data to the smart bracelet in real time via the helmet's Bluetooth module. Simultaneously, after completing a thermal comfort assessment or receiving control commands from a management terminal, the smart bracelet can send a warning control command to the smart helmet, triggering the helmet's built-in vibration and LED modules to provide local alerts or alarms to the worker.

[0084] The smart tool and the smart bracelet establish a connection via Bluetooth. The ambient temperature and humidity detection modules within the smart tool collect real-time temperature and humidity parameters of the working environment and upload these parameters to the smart bracelet. When needed, the smart bracelet can send operation control commands to the smart tool to control its operating status or parameter collection cycle, thereby achieving collaborative perception of environmental information.

[0085] The smart bracelet and the management terminal exchange data bidirectionally via a wireless communication network. The smart bracelet uploads the aggregated physiological parameters, environmental parameters, thermal comfort assessment results, and location information of the workers to the management terminal for centralized storage, analysis, and risk assessment. Based on the analysis results, the management terminal issues control commands to the smart bracelet, including early warning prompts, work adjustment suggestions, and area control information. Upon receiving the control commands, the smart bracelet can further coordinate with the smart safety helmet to execute corresponding warning actions.

[0086] Through the above data interaction methods, a multi-device collaborative working mechanism with the smart bracelet as the core is realized, enabling the efficient flow of physiological information, environmental information and thermal comfort assessment results between the local end and the management end. This not only meets the real-time requirements of underground operation scenarios, but also takes into account the needs of centralized management and remote safety control, thereby improving the overall reliability and practicality of thermal comfort monitoring and risk warning for mine workers.

[0087] Reference Figure 1In another aspect, this embodiment provides a method for detecting human thermal comfort using the above-mentioned detection device, comprising the following steps:

[0088] S1: Establish a thermal comfort assessment model; deploy the thermal comfort assessment model to the wristband's local processing module;

[0089] The process of establishing the thermal comfort assessment model includes the following steps:

[0090] S11: Questionnaire Survey

[0091] Three representative high-altitude mines were selected as research subjects. Questionnaire surveys and basic information collection were conducted among the workers. Subjective thermal sensations, comfort evaluations, and personal basic information of the workers under different environmental conditions, labor intensity, and working hours were obtained. Combined with corresponding environmental parameters and working condition data, a thermal comfort assessment sample library for high-altitude mine working scenarios was constructed. This thermal comfort assessment sample library serves as the basic data support for the establishment of thermal comfort assessment models, parameter correction, and result verification.

[0092] S12: Sample Collection

[0093] Core physiological and environmental parameters for thermal assessment were collected using smart bracelets, smart workwear, and smart safety helmets. A web-based questionnaire sent via the smart bracelets collected data on participants' gender, age, clothing thermal resistance, activity intensity, and thermal sensation voting. Forehead temperature, heart rate, blood oxygen, pulse, ambient temperature, ambient humidity, clothing thermal resistance, and human activity status were collected as input samples. Human thermal sensation was quantified into thermal sensation voting values, and the corresponding thermal comfort levels were collected as output samples via the web-based questionnaire. More than 1000 valid questionnaires were collected, forming the input-output sample pairs required for supervised learning.

[0094] S13: Data Preprocessing

[0095] The raw data was cleaned, outliers were removed using box plots, and missing values ​​were filled using Lagrange interpolation to ensure the quality of the training samples. Next, feature selection was performed, removing low-variance and highly correlated features and retaining nine effective features: ambient temperature, ambient humidity, heart rate, blood oxygen, pulse, forehead temperature, clothing thermal resistance, work intensity, and personnel identity. Normalization was then applied. Finally, the dataset was split: stratified sampling was performed in a 7:3 ratio to create training and testing sets. Numerical features were standardized to unify features of different dimensions into a trainable range. Thermal comfort levels were discretized into classification labels, and these labels were then used to divide the training and testing sets in a 7:3 ratio for model training and evaluation.

[0096] S14: Model Training and Optimization

[0097] Multiple classification models were constructed using logistic regression, random forest, gradient boosting decision tree, and support vector machine algorithms. The model parameters were optimized through cross-validation and grid search to select the model with the best performance.

[0098] S15: Model Deployment and Real-Time Application

[0099] The trained optimal model is lightweighted and then deployed to the local processing module of the wristband to achieve real-time calculation at the edge. During the application, the multi-dimensional core thermal parameters collected in real time are used as input samples to input the model and output the thermal comfort level of the current worker.

[0100] S2: Connect smart bracelets, smart work clothes, and smart safety helmets via Bluetooth, and bind worker information to the smart bracelets;

[0101] Before workers enter the mine, the smart bracelet unit automatically generates a recognizable QR code. At the mine entrance, the facial recognition device scans the QR code generated by the smart bracelet while verifying the worker's identity. This associates and binds the worker's identity information (name, employee number, position, etc.) with the unique identification information of the smart bracelet, smart work clothes, and safety helmet. The binding information is simultaneously uploaded to the management terminal and stored, achieving a one-to-one mapping between "personnel and equipment" to ensure that all data collected subsequently can be traced back to the specific worker.

[0102] S3: The smart bracelet, smart tooling and smart safety helmet are used to monitor the physiological parameters, psychological parameters and underground environmental parameters of the workers respectively. All parameters are summarized to the local processing module of the bracelet.

[0103] The smart bracelet worn by workers collects human physiological parameters in real time; its heart rate detection module, blood oxygen detection module, and pulse detection module are used to collect the workers' heart rate, blood oxygen, and pulse data, respectively.

[0104] The system uses smart workwear worn by workers to collect downhole environmental parameters in real time. The environmental temperature detection module and the environmental humidity detection module are used to collect air temperature and air humidity data in the work area, respectively. The data obtained are then aggregated to a smart bracelet via Bluetooth.

[0105] The forehead temperature detection module at the bottom of the visor of the smart safety helmet worn by the worker collects forehead temperature data in real time and aggregates it to the smart bracelet via Bluetooth.

[0106] The psychological parameters of workers are obtained through the interactive module of the smart bracelet, including thermal sensation voting information and thermal comfort satisfaction evaluation information.

[0107] S4: The thermal comfort assessment model is called through the local processing module of the wristband, and the current thermal comfort level is obtained based on the parameters obtained in S3; and a graded warning is triggered according to the thermal comfort level.

[0108] The display module is a touch-screen display module. The real-time data obtained is displayed through the display module. Users can switch screen pages and view various detailed data through touch operation. The data includes the human forehead temperature, heart rate, blood oxygen, pulse, ambient temperature, and ambient humidity collected in step S3, the thermal comfort level generated in step S4, and the information sent by the management terminal.

[0109] The thermal comfort level is divided into seven levels: hot, warm, slightly warm, moderate, slightly cool, cool, and cold. Based on changes in parameters such as blood oxygen and heart rate, the display module matches the human body's thermal comfort level with four safety colors in real time according to the level of danger, enabling intuitive identification of the risk status. Specifically, the correspondence is as follows: severe abnormality level ("hot" or "cold" in the thermal comfort level) is displayed in red; mild abnormality level ("warm" or "cool" in the thermal comfort level) is displayed in yellow; normal level ("slightly warm" or "slightly cool" in the thermal comfort level) is displayed in blue; and comfortable level ("moderate" in the thermal comfort level) is displayed in green. The safety colors are displayed synchronously with the text information of the thermal comfort level, and the color brightness is adapted to the complex lighting environment underground, ensuring that workers can quickly identify the current thermal comfort risk status.

[0110] The smart bracelet transmits the aforementioned data to the management terminal in real time via its wireless communication module. The management terminal then categorizes and stores the data, creating a personal thermal comfort history database for each worker. More specifically, the smart bracelet's built-in wireless communication module transmits the data in real time, storing it on the management terminal's server. Based on verified data, the management terminal stores the data in its database according to a three-level structure: "personnel dimension - time dimension - data type dimension." The local server stores the raw data in real time, and it is automatically synchronized to cloud storage every morning.

[0111] The system obtains the real-time location information of the workers through the positioning module and triggers graded early warnings based on the thermal comfort level. More specifically, the system obtains the real-time location information of the workers through the positioning module and combines it with the thermal comfort level output in step S4. If an abnormal state is determined, a graded early warning mechanism is triggered: when the abnormality is mild, a prompt signal is sent to the smart bracelet worn by the workers, and the built-in vibration module of the safety helmet worn by the workers emits a low-frequency prompt, and the LED module of the smart safety helmet emits a low-frequency flashing; when the abnormality is severe, an alarm signal is sent to the management terminal simultaneously, the real-time location information is uploaded, and the built-in vibration module of the safety helmet emits a high-frequency alarm, the LED module of the smart safety helmet emits a high-frequency flashing, and emergency response measures are activated in conjunction with the system.

[0112] Based on the real-time location information of workers and corresponding abnormal thermal comfort status data obtained in the above steps, the management terminal dynamically delineates dangerous and safe zones and executes control commands. More specifically, based on the obtained real-time location information of workers and corresponding abnormal thermal comfort status data, combined with the environmental parameter distribution characteristics of the mine operation area, the management terminal delineates dangerous and safe zones: if an area is determined to be a dangerous zone, the management terminal sends a "stop work, evacuate immediately" command to the smart bracelets and safety helmets of all workers in that area, and simultaneously shuts down non-essential work equipment in that area through the mine control system; if an area is determined to be a safe zone, the management terminal sends a "work can continue" prompt and dynamically updates the area's safety status to the mine control system, realizing dynamic safety control of the operation area.

[0113] The management terminal integrates stored historical information about workers with transmitted real-time data to comprehensively assess the worker's current physical condition and suitability for continuous work, outputting a binary decision result: "Recommend continuing work" or "Recommend pausing for rest." This decision result is simultaneously pushed to the worker's smart bracelet and safety helmet. More specifically, the management terminal combines stored historical thermal comfort information with currently collected thermal comfort data—that is, the worker's historical heat tolerance in similar environments, recovery period from past abnormal conditions, and current continuous work duration—using AI to comprehensively analyze and assess the user's current physical condition, outputting a decision result of "Recommend continuing work" or "Recommend pausing for rest." If the result is "Recommend pausing for rest," the decision result is simultaneously pushed to the worker's smart bracelet and vibration module as an auxiliary basis for work scheduling, achieving individualized and dynamic work status management.

[0114] In summary, although the present invention has been disclosed above with reference to preferred embodiments, the above preferred embodiments are not intended to limit the present invention. Those skilled in the art will know that the present invention can have various modifications and variations. Various modifications and refinements can be made without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be determined by the scope defined in the claims.

Claims

1. A portable, digitally-enabled, wearable device for detecting human thermal comfort, characterized in that: The system includes a smart bracelet, smart tooling, a smart safety helmet, a wireless communication module, and a management terminal. The smart bracelet, smart tooling, and smart safety helmet are interconnected via Bluetooth, and the smart bracelet and management terminal are electrically connected via the wireless communication module. The smart bracelet is equipped with a thermal comfort assessment model. The smart bracelet, smart tooling, and smart safety helmet monitor the physiological parameters, psychological parameters, and underground environmental parameters of the workers, respectively. All parameters are aggregated in the smart bracelet, which then calls the thermal comfort assessment model to determine the current thermal comfort level based on the collected physiological, psychological, and underground environmental parameters. And trigger graded warnings based on thermal comfort levels.

2. The portable intelligent human thermal comfort detection device according to claim 1, characterized in that: The smart bracelet includes a main body, a heart rate detection module, a blood oxygen detection module, a pulse detection module, a Bluetooth module, a wireless communication module, a display module, an interaction module, a local processing module, a positioning module, and a battery. The heart rate detection module, blood oxygen detection module, pulse detection module, display module, interaction module, positioning module, Bluetooth module, and wireless communication module are electrically connected to the local processing module. The battery powers all the power-consuming modules of the smart bracelet.

3. The portable intelligent human thermal comfort detection device according to claim 2, characterized in that: The intelligent tooling includes an intelligent tooling body, main intelligent tooling equipment, tooling switch, ambient temperature detection module, ambient humidity detection module, tooling local processing module, tooling Bluetooth module, and tooling battery; the ambient temperature detection module and ambient humidity detection module are electrically connected to the tooling local processing module, and the tooling battery supplies power to each power-consuming module of the intelligent tooling and controls its on / off state through the tooling switch.

4. The portable intelligent human thermal comfort detection device according to claim 3, characterized in that: The smart safety helmet includes a main body, a switch, an LED module, a vibration module, a forehead temperature detection module, a Bluetooth module, a microcontroller module, and a battery. The LED module, vibration module, and forehead temperature detection module are electrically connected to the microcontroller module. The battery supplies power to all the electrical modules of the smart safety helmet and controls their on / off states through the switch.

5. A method for detecting human thermal comfort on a personal device using the detection device as described in claim 4, characterized in that: Includes the following steps: S1: Establish a thermal comfort assessment model; deploy the thermal comfort assessment model to the wristband's local processing module; S2: Connect smart bracelets, smart work clothes, and smart safety helmets via Bluetooth, and bind worker information to the smart bracelets; S3: The smart bracelet, smart tooling and smart safety helmet are used to monitor the physiological parameters, psychological parameters and underground environmental parameters of the workers respectively. All parameters are summarized to the local processing module of the bracelet. S4: The thermal comfort assessment model is called through the local processing module of the wristband, and the current thermal comfort level is obtained based on the parameters obtained in S3; And trigger graded warnings based on thermal comfort levels.

6. The method for detecting human thermal comfort on a personal device according to claim 5, characterized in that: The process of establishing the thermal comfort assessment model includes the following steps: S11: Questionnaire Survey Three representative high-altitude mines were selected as research subjects. Questionnaire surveys and basic information collection were conducted among the workers. Subjective thermal sensations, comfort evaluations, and personal basic information of the workers under different environmental conditions, labor intensity, and working hours were obtained. Combined with corresponding environmental parameters and working condition data, a thermal comfort assessment sample library for high-altitude mine working scenarios was constructed. This thermal comfort assessment sample library serves as the basic data support for the establishment of thermal comfort assessment models, parameter correction, and result verification. S12: Sample Collection Core physiological and environmental parameters for thermal assessment were collected using smart bracelets, smart workwear, and smart safety helmets. A web-based questionnaire sent via the smart bracelets collected data on participants' gender, age, clothing thermal resistance, activity intensity, and thermal sensation voting. Forehead temperature, heart rate, blood oxygen, pulse, ambient temperature, ambient humidity, clothing thermal resistance, and human activity status were collected as input samples. Human thermal sensation was quantified into thermal sensation voting values, and the corresponding thermal comfort levels were collected as output samples via the web-based questionnaire. More than 1000 valid questionnaires were collected, forming the input-output sample pairs required for supervised learning. S13: Data Preprocessing The raw data was cleaned, outliers were removed using box plots, and missing values ​​were filled using Lagrange interpolation to ensure the quality of the training samples. Next, feature selection was performed, removing low-variance and highly correlated features and retaining nine effective features: ambient temperature, ambient humidity, heart rate, blood oxygen, pulse, forehead temperature, clothing thermal resistance, work intensity, and personnel identity. Normalization was then applied. Finally, the dataset was split: stratified sampling was performed in a 7:3 ratio to create training and testing sets. Numerical features were standardized to unify features of different dimensions into a trainable range. Thermal comfort levels were discretized into classification labels, and these labels were then used to divide the training and testing sets in a 7:3 ratio for model training and evaluation. S14: Model Training and Optimization Multiple classification models were constructed using logistic regression, random forest, gradient boosting decision tree, and support vector machine algorithms. The model parameters were optimized through cross-validation and grid search to select the model with the best performance. S15: Model Deployment and Real-Time Application The trained optimal model is lightweighted and then deployed to the local processing module of the wristband to achieve real-time calculation at the edge. During the application, the multi-dimensional core thermal parameters collected in real time are used as input samples to input the model and output the thermal comfort level of the current worker.

7. The method for detecting human thermal comfort on a personal device according to claim 5, characterized in that: The real-time data obtained from S3 is transmitted to the management terminal via the wireless communication module. The management terminal classifies and stores the data to form a personal thermal comfort history database for each worker. The management terminal integrates the stored historical information of the workers with the transmitted real-time data to comprehensively assess the suitability of the worker's current physical condition for continuous work and outputs a binary decision result: "It is recommended to continue working" or "It is recommended to take a break". The decision result is simultaneously pushed to the worker's smart bracelet and safety helmet.

8. The method for detecting human thermal comfort on a personal device according to claim 5, characterized in that: The positioning module obtains the real-time location information of the workers. Based on the obtained real-time location information of the workers and the corresponding thermal comfort status data, the management terminal dynamically delineates dangerous areas and safe areas and executes control commands.

9. The method for detecting human thermal comfort on a personal device according to claim 5, characterized in that: Before workers go down into the mine, the smart bracelet automatically generates a recognizable QR code. At the mine entrance, the facial recognition device scans the QR code generated by the smart bracelet while verifying the worker's identity, thus associating and binding the worker's identity information with the unique identification information of the smart bracelet, smart work clothes, and safety helmet. The binding information is synchronously uploaded to the management terminal storage.

10. The method for detecting human thermal comfort on a personal device according to claim 5, characterized in that: In step S4, on the one hand, the real-time location information of the worker is obtained through the positioning module. Combined with the thermal comfort level output in step S4, if an abnormal state is determined, a graded early warning mechanism is triggered: when it is a mild abnormality, a prompt signal is sent to the smart bracelet worn by the worker, and the vibration module built into the safety helmet worn by the worker emits a low-frequency prompt, and the LED module of the smart safety helmet emits a low-frequency flash; when it is a severe abnormality, an alarm signal is sent to the management terminal simultaneously, the real-time location information is uploaded, and the vibration module built into the safety helmet emits a high-frequency alarm, the LED module of the smart safety helmet emits a high-frequency flash, and emergency response measures are activated in conjunction with the alarm. On the other hand, in combination with changes in physiological parameters, the display module displays the human thermal comfort level in real time according to the danger level, matching four safety colors to achieve intuitive identification of the risk status. The specific correspondence is as follows: severe abnormality level is displayed in red, mild abnormality level is displayed in yellow, normal level is displayed in blue, and comfort level is displayed in green. The safety colors and thermal comfort level text information are displayed synchronously, and the color brightness is adapted to the complex lighting environment underground, ensuring that the worker can quickly identify the current thermal comfort risk status.

Images